遥感数据专题分类不确定性评价研究：进展、问题与展望

doi:10.11867/j.issn.1001-8166.2005.11.1218

地球科学进展 ›› 2005, Vol. 20 ›› Issue (11): 1218 -1225. doi: 10.11867/j.issn.1001-8166.2005.11.1218

柏延臣 ¹，王劲峰 ²

1．北京师范大学地理学与遥感科学学院遥感与GIS研究中心，遥感信息科学国家重点实验室，环境遥感与数码城市北京市重点实验室，北京 100875；2．中国科学院地理科学与资源研究所，北京 100101

收稿日期:2004-12-09 修回日期:2005-07-11 出版日期:2005-11-25
通讯作者: 柏延臣
基金资助:
国家自然科学基金项目“遥感分类专题信息的不确定性评价关键问题研究”（编号：40301033）；国家自然科学基金项目“基于机理的遥感信息不确定性分析及可视化表达”（编号：40201033）；国家863项目“GIS和遥感产品质量评价标准研究及系统实现”（编号：001AA135151）；中国博士后科学基金项目“像元尺度上的遥感分类不确定性评价及可视化研究”（编号：2003033111）；北京师范大学青年科学基金共同资助.

ASSESSMENT ON UNCERTAINTY IN REMOTELY SENSED DATA CLASSIFICATION: PROGRESSES, PROBLEMS AND PROSPECTS

BO Yanchen ¹,WANG Jinfeng ²

1.Research Center for Remote Sensing and GIS, School of Geography, Beijing Normal University, State Key Laboratory of Remote Sensing Science, Beijing Key Laboratory for Remote Sensing of Environment and Digital Cities, Beijing 100875,China;2. Institute of Geographical Science and Natural Resources Research,Chinese Academy of Sciences, Beijing 100101, China

Received:2004-12-09 Revised:2005-07-11 Online:2005-11-25 Published:2005-11-25

下载PDF ( 2185 )

从遥感数据中提取专题类别信息是当前遥感数据最主要的应用领域之一。由于遥感分类专题信息广泛应用于各种领域，其数据质量受到越来越多的关注。不确定性是评价分类专题类别数据质量最主要的方面。回顾了遥感数据专题分类不确定性评价方法的历史，总结了当前各种评价方法及其指标体系，将这些方法归结为基于误差矩阵的方法、模糊评价方法、像元尺度上的不确定性评价方法和其它方法四大类。对每一类不确定性评价方法及其指标体系的优点和缺点进行了分析和总结，指出从理论方法研究方面，需要优先发展独立于分类方法的像元尺度上的遥感分类不确定性评价模型与指标体系，以及统一的遥感数据分类不确定性评价模型体系研究；在应用研究方面，需要加强优化空间采样设计和不确定性评价过程标准化研究。

关键词: 遥感数据分类, 不确定性, 误差矩阵, 模糊评价, 像元尺度的评价

Thematic mapping is one of the major application fields of remote sensing techniques. Due to the wide use of the thematic data derived from remotely sensed data by either visual interpretation or automatic classification, data quality of the thematic data was concerned about. Uncertainty in the classified remotely sensed data is one of the most important elements of the data quality. In this paper, the development of the methods for assessment of uncertainty in remotely sensed data classification was overviewed, existing methods and the uncertainty measurements were reviewed and categorized into error matrix based methods, fuzzy set based methods, methods of assessment at pixel scale and other methods. Advantages and the problems remained in every kind of method were analyzed. Future research was suggested that, from the perspective of theoretic study, the uncertainty assessment method at pixel scale and the uncertainty measurements independent on the classifier should be developed; from the perspective of application, attentions should be paid on the optimal spatial sampling and the standardization of uncertainty assessment procedures.

Key words: Uncertainty, Uncertainty assessment at pixel scale., Remote sensing, Classification, Error matrix, Fuzzy accuracy Assessment

中图分类号:

TP79

［1］Sun Shu. Earth date-An important resources for geoscience innovation[J].Edvances in Earth Science,2003, 18(3): 334-337.[孙枢.地球数据是地球科学创新的重要源泉——从地球科学谈科学数据共享[J]. 地球科学进展,2003, 18(3): 334-337.]
［2］Arnoff S. The map accuracy report: A user’s view [J]. Photogrammetric Engineering and Remote Sensing, 1982, 48(8): 1 309-1 312.
［3］Arnoff S. The minimum accuracy value as an index of classification accuracy [J]. Photogrammetric Engineering and Remote Sensing, 1985, 51 (1): 593-600.
［4］Congalton R G. A review of assessing the accuracy of classifications of remotely sensed data [J]. Remote Sensing of Environment, 1991, 37:35-46.［5］Congalton R G, Green K. Assessing the Accuracy of Remotely Sensed Data: Principles and Practices [M]. Boca Rato: Lewis Publishers, 1999.
［6］Ma Z, Redmond R L. Tau coefficients for accuracy assessment of classification of remote sensing data [J]. Photogrammetric Engineering and Remote Sensing, 1995, 61 (4):435-439.
［7］Nasset E. Conditional Tau Coefficient for assessment of producer's accuracy of classified remotely sensed data [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1996, 51: 91-98.
［8］Richards J A. Classifier performance and map accuracy [J]. Remote Sensing of Environment, 1996, 57(1):161-166.
［9］Stehman S V. Comparing thematic maps based on map value [J]. International Journal of Remote Sensing, 1999, 20:2 347-2 366.
［10］Turk G. Gt Index: A measure of the success of prediction [J]. Remote Sensing of Environment,1979, 8:65-75.
［11］Gopal S, Woodcock C. Theory and methods for accuracy assessment of thematic maps using fuzzy sets [J]. Photogrammetric Engineering and Remote Sensing, 1994, 60:181-188.
［12］Townsend P A. A quantitative fuzzy approach to assess mapped vegetation classifications for ecological applications [J]. Photogrammetric Engineering and Remote Sensing,2000, 72:253-267.
［13］Foody G M. Cross-entropy for the evaluation of the accuracy of a fuzzy land cover classification with fuzzy ground data [J]. ISPRS Journal of Photogrammetry and Remote Sensing,1995, 50(5):2-12.
［14］Gunther J, Benz U. Measures of classification accuracy based on fuzzy similarity [J]. IEEE Transactions on Geoscience and Remote Sensing,2000, 38(3):1 462-1 467.
［15］Goodchild M F, Sun G ,Yang S. Development and test of an error model for categorical data [J]. International Journal of Geographical Information Systems, 1992, 6(2):87-104.
［16］Shi Wenzhong. Theory and Method of Error Processing in Spatial Data[M]. Beijing: Science Press, 1998.[史文中.空间数据误差处理的理论与方法 [M]. 北京：科学出版社, 1998.]
［17］Maselli F, Conese C, Petkov L. Use of probability entropy for the estimation and graphical representation of the accuracy of maximum likelihood classifications [J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1994, 49(2):13-20.
［18］Foody G M. Approaches for the production and evaluation of fuzzy land cover classifications from remotely sensed data [J]. International Journal of Remote Sensing, 1996, 17(7):1 317-1 340.
［19］Zhu A X. Measuring uncertainty in class assignment for natural resource maps under fuzzy logic [J]. Photogrammetric Engineering and Remote Sensing, 1997, 63:1 195-1 202.
［20］Steele B M, Winne J C, Redmond R L. Estimation and mapping of misclassification probabilities for thematic land cover maps [J]. Remote Sensing of Environment, 1998, 66: 192-202.
［21］McIver D K, Friedl M A. Estimating pixel-scale land cover classification confidence using nonparametric machine learning methods [J]. IEEE Transactions on Geoscience and Remote Sensing,2001, 39(9):1 959-1 968.
［22］Rosenfield G H. Analysis of variance of thematic mapping experiment data[J].Photogrammetric Engineering and Remote Sensing,1981, 47(12):1 685-1 692.
［23］Smits P C, Dellepiane S G, Schowengerdt R A. Quality assessment of image classification algorithms for land-cover mapping: A review and proposal for a cost-based approach[J].International Journal of Remote Sensing,1999, 20:1 461-1 486.
［24］Stehman S V. Estimating the kappa coefficient and its variance under stratified random sampling [J].Photogrammetric Engineering and Remote Sensing,1996, 62(4):401-407.
［25］Congalton R G, Oderwald, Mead R. Landsat classification accuracy using discrete multivariate analysis statistical techniques [J]. Photogrammetric Engineering and Remote Sensing,1983,49:1 671-1 678.
［26］Lanter D P, Veregin H. A research paradigm for propagating error in layer-based GIS [J]. Photogrammetric Engineering and Remote Sensing,1992, 58(6):825-833.
［27］Michele C, Jose A M R, Bruno C. Uncertainty propagation in models driven by remotely sensed data [J]. Remote Sensing of Environment,2001, 76:373-385.
［28］Foody G M. Status of land cover classification accuracy assessment [J]. Remote Sensing of Environment, 2002, 80:185-201.
［29］Foody G M. On the compensation for chance agreement in image classification accuracy assessment [J].Photogrammetric Engineer and Remote Sensing,1992, 58(10):1 459-1 460.
［30］Stehman S V, Czaplewski R L. Design and analysis for thematic map accuracy assessment: Fundamental principles [J]. Remote Sensing of Environment,1998, 64:331-344.
［31］Stehman S V. Selecting and interpreting measures of thematic classification accuracy [J]. Remote Sensing of Environment,1997, 62:77-89.
［32］Muller S V, Walker D A. Accuracy assessment of a land-cover map of the Kuparuk river basin, Alaska: Considerations for remote regions [J].Photogrammetric Engineering and Remote Sensing,1998, 64:619-628.
［33］Stehman S V. Basic probability sampling designs for thematic map accuracy assessment [J].International Journal of Remote Sensing,1999, 20:2 423-2 441.
［34］Lunetta R S, Iiames J, Knight J, et al. An assessment of reference data variability using a “virtual field reference database”[J]. Photogrammetric Engineering and Remote Sensing,2001, 63:707-715.
［35］Fitzgerald R W, Lees B G. Assessing the classification accuracy of multisource remote sensing data [J]. Remote Sensing of Environment, 1994, 47:362-368.
［36］Justice C, Belward A, Morisette J, et al. Developments in the validation' of satellite sensor products for the study of the land surface [J]. International Journal of Remote Sensing, 2000, 21:3 383-3 390.
［37］Thomlinson J R, Bolstad P V,Cohen W B. Coordinating methodologies for scaling land cover classifications from site-specific to global: Steps toward validating global map products [J]. Remote Sensing of Environment, 1999, 70: 16-28.
［38］Scepan J. Thematic validation of high-resolution global land-cover data sets [J]. Photogrammetric Engineering and Remote Sensing, 1999, 65:1 051-1 060.
［39］Czaplewsi R L. Misclassification bias in areal estimates [J]. Photogrammetric Engineering and Remote Sensing, 1992, 58: 189-192.
［40］Lewis H G, Brown M. A generalized confusion matrix for assessing area estimates from remotely sensed data [J]. International Journal of Remote Sensing, 2001, 22 (16):3 223-3 235.
［41］Defries R S, Los S O. Implications of land-cover misclassification for parameter estimates in global land-surface models: An example from the simple biosphere model(SiB₂)[J]. Photogrammetric Engineering and Remote Sensing, 1999, 65:1 083-1 088.
［42］Fisher P E. Visualization of the reliability in classified remotely sensed images [J]. Photogrammetric Engineering and Remote Sensing, 1994, 60:905-910.
［43］Van der Wel, Gorte B G H. Visual exploration of uncertainty in remote sensing classification [J]. Computer and Geosciences,1998, 24(4):335-343.［44］Knight J, Khorram S. Accuracy assessment of thematic data using fuzzy sets and inter-class spectral distances [A]. In: Heuvelink G B M, Iemmens M J P M, eds. Proceedings of the 4th International Symposium on Spatial Accuracy Assessment in Natural Resources and Environmental sciences[C]. Delft: Delft University Press, 2000.359-364.
［45］Wang J, Liu J, Zhuang D, et al. Spatial Sampling design for monitoring the area of cultivated land [J]. International Journal of Remote Sensing, 2002, 23 (2): 263-284.

[1]	单薪蒙, 温家洪, 王军, 胡恒智. 深度不确定性下的灾害风险稳健决策方法评述[J]. 地球科学进展, 2021, 36(9): 911-921.
[2]	尤元红,黄春林,张莹,侯金亮. Noah-MP模型中积雪模拟对参数化方案的敏感性评估[J]. 地球科学进展, 2019, 34(4): 356-365.
[3]	马晋, 周纪, 刘绍民, 王钰佳. 卫星遥感地表温度的真实性检验研究进展[J]. 地球科学进展, 2017, 32(6): 615-629.
[4]	卿文武, 刘俊峰, 杨钰泉, 陈仁升, 韩春坛. 基于气温的物质平衡模型的参数不确定性分析——以祁连山十一冰川为例[J]. 地球科学进展, 2016, 31(9): 937-945.
[5]	鲁易, 张稳, 李婷婷, 周筠珺. 大气甲烷浓度变化的源汇因素模拟研究进展[J]. 地球科学进展, 2015, 30(7): 763-772.
[6]	王辉, 刘娜, 李本霞, 李响. 海洋可预报性和集合预报研究综述[J]. 地球科学进展, 2014, 29(11): 1212-1225.
[7]	彭建, 刘焱序, 潘雅婧, 赵志强, 宋治清, 王仰麟. 基于景观格局—过程的城市自然灾害生态风险研究：回顾与展望[J]. 地球科学进展, 2014, 29(10): 1186-1196.
[8]	覃荣高, 曹广祝, 仵彦卿. 非均质含水层中渗流与溶质运移研究进展 ^*[J]. 地球科学进展, 2014, 29(1): 30-41.
[9]	宋焱，徐颂军，张勇，廖秀英，张林英，杨秀，杨文槐，冯晓丹. 白云山地表水重金属健康风险不确定性评价[J]. 地球科学进展, 2013, 28(9): 1036-1042.
[10]	胡宁科，李新. 历史时期土地利用变化研究方法综述[J]. 地球科学进展, 2012, 27(7): 758-768.
[11]	岳跃民, 王克林, 张兵，刘波, 陈洪松, 张明阳. 喀斯特石漠化信息遥感提取的不确定性[J]. 地球科学进展, 2011, 26(3): 266-274.
[12]	方修琦,王媛,魏本勇,王文琴. 中国进出口贸易碳转移排放测算方法分析与评价[J]. 地球科学进展, 2011, 26(10): 1101-1108.
[13]	陈泮勤,程邦波,王芳,曲建升. 全球气候变化的几个关键问题辨析[J]. 地球科学进展, 2010, 25(1): 69-75.
[14]	陈玲,阎广建,李静,余莹洁. 行播作物地面方向性测量的视场不确定性分析[J]. 地球科学进展, 2009, 24(7): 793-802.
[15]	张睿,马建文. 支持向量机在遥感数据分类中的应用新进展[J]. 地球科学进展, 2009, 24(5): 555-562.

阅读次数

全文

摘要